Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ຊ
    -0.07
    乸
    -0.07
     strm
    -0.06
    _asset
    -0.06
    -Nazi
    -0.06
    觐
    -0.06
    迷惑
    -0.06
    高潮
    -0.06
     Central
    -0.06
    hydration
    -0.06
    POSITIVE LOGITS
    ϕ
    0.07
    .her
    0.07
     //
↵
↵
    0.07
    สย
    0.07
    ,
↵
    0.07
    tgt
    0.06
     hx
    0.06
     соб
    0.06
     rgba
    0.06
    ω
    0.06
    Act Density 0.001%

    No Known Activations